A study measures baseline blood pressure, then undergoes an exercise program for a month, and blood pressure is measured again. Which test assesses whether the program changed blood pressure?

A study measures baseline blood pressure, then undergoes an exercise program for a month, and blood pressure is measured again. Which test assesses whether the program changed blood pressure?

• A. Matched pairs t-test
• B. Two-sample t-test
• C. Wilcoxon signed-rank test
• D. ANOVA for repeated measures

Answer: (A)

When the same individuals are measured twice, you’re interested in how each person changes rather than comparing two independent groups. A paired (matched) t-test compares the mean of the differences between the two measurements. Here, you’d look at how each subject’s blood pressure changes from baseline to after the month of exercise and test whether that average change is significantly different from zero. This approach accounts for the fact that the two measurements are linked within each person, increasing sensitivity to detect a real effect. If the differences don’t look normally distributed, the nonparametric alternative is the Wilcoxon signed-rank test. ANOVA for repeated measures would be used if there were three or more time points or conditions, making the paired t-test unnecessary for just baseline and post-intervention data.

When the same individuals are measured twice, you’re interested in how each person changes rather than comparing two independent groups. A paired (matched) t-test compares the mean of the differences between the two measurements. Here, you’d look at how each subject’s blood pressure changes from baseline to after the month of exercise and test whether that average change is significantly different from zero. This approach accounts for the fact that the two measurements are linked within each person, increasing sensitivity to detect a real effect. If the differences don’t look normally distributed, the nonparametric alternative is the Wilcoxon signed-rank test. ANOVA for repeated measures would be used if there were three or more time points or conditions, making the paired t-test unnecessary for just baseline and post-intervention data.